P
US12197880B2ActiveUtilityPatentIndex 49

Systems and methods for translating transaction descriptions

Assignee: CAPITAL ONE SERVICES LLCPriority: Dec 18, 2020Filed: Dec 18, 2020Granted: Jan 14, 2025
Est. expiryDec 18, 2040(~14.5 yrs left)· nominal 20-yr term from priority
Inventors:OLSEN SARAHPAI ADITYAELDER BRICE
G06N 3/09G06N 3/0442G06N 3/091G06N 3/0455G06F 40/47G06N 3/04G06N 3/045G06N 3/044G06F 40/58G06F 40/42
49
PatentIndex Score
0
Cited by
15
References
19
Claims

Abstract

Disclosed embodiments may include a method that includes receiving description data in an originating language for a user and a location associated with the user, identifying one or more names from the description data, retrieving additional data in the originating language based on the one or more names, generating enhanced description data in the originating language for the user based on the description data and the additional data, identifying a target language based on the location associated with the user, selecting a first trained neural network from a plurality of trained neural networks based the target language, providing the enhanced description data in the originating language to the first trained neural network, translating, via the first trained neural network, the enhanced description data from the originating language to the target language, and generating a graphical user interface for display that comprises the enhanced description data in the target language.

Claims

exact text as granted — not AI-modified
What is claimed is: 
     
       1. A system, comprising:
 one or more processors; and 
 a memory in communication with the one or more processors and storing instructions are configured to cause the system to:
 receive or retrieve (i) transaction description data in an originating language, the transaction description data associated with one or more transactions made by a user, and (ii) a location associated with the user from a payment processing server; 
 for each transaction of the one or more transactions made by the user in the originating language during a predetermined period of time:
 identify one or more names from the transaction description data; 
 retrieve additional data in the originating language based on the one or more names; 
 generate enhanced description data in the originating language for the user based on the transaction description data and the additional data; 
 identify a target language based on the location associated with the user; 
 select a first trained neural network from a plurality of trained neural networks based on the target language; 
 provide the enhanced description data in the originating language to the first trained neural network; and 
 translate, via the first trained neural network, the enhanced description data from the originating language to the target language; 
 
 generate a first graphical user interface (GUI) comprising:
 the enhanced description data for each transaction of the one or more transactions in the target language during the predetermined period of time; and 
 a selectable option associated with each transaction of the one or more transactions; 
 
 receive an indication, via the first GUI, that the user selected the selectable option associated with a first transaction of the one or more transactions; and 
 responsive to receiving the indication, cause the first GUI to additionally display the enhanced description data associated with the first transaction in the originating language. 
 
 
     
     
       2. The system of  claim 1 , wherein the first trained neural network comprises a recurrent neural network. 
     
     
       3. The system of  claim 2 , wherein the recurrent neural network comprises an encoder and a decoder. 
     
     
       4. The system of  claim 1 , wherein identifying the target language comprises retrieving the location associated with the user and matching the location with a first location from a predetermined list of locations associated with the target language. 
     
     
       5. The system of  claim 1 , wherein:
 the enhanced description data further comprises a map, and 
 the selectable option comprises a button. 
 
     
     
       6. The system of  claim 1 , wherein the additional data comprises an address, a phone number, an email, and a uniform resource locator. 
     
     
       7. The system of  claim 1 , wherein the instructions are further configured to cause the system to transmit the first GUI to a user device associated with the user for display. 
     
     
       8. The system of  claim 7 , wherein the instructions are further configured to cause the system to:
 receive feedback instructions related to an accuracy of the enhanced description data in the target language from the user device; and 
 train the first trained neural network based on the feedback instructions. 
 
     
     
       9. The system of  claim 1 , wherein:
 the transaction made by the user is associated with a purchase made using a debit card or a credit card, 
 the additional data includes a merchant location based on the one or more names, and 
 the instructions are further configured to cause the system to:
 identify the originating language based on the merchant location. 
 
 
     
     
       10. A system, comprising:
 one or more processors; and 
 a memory in communication with the one or more processors and storing instructions are configured to cause the system to:
 receive or retrieve (i) raw transaction description data in one or more originating languages, the raw transaction description data associated with one or more transactions made by a user from a payment processing server within a predetermined period of time, (ii) additional data in the originating language, and (iii) a location of the user; 
 for each transaction of the one or more transactions made by the user in each originating language of the one or more originating languages during a predetermined period of time:
 generate enhanced description data in the originating language for the user based on the raw transaction description data and the additional data; 
 identify a target language based on the location associated with the user; 
 select a trained neural network from a plurality of trained neural networks based on the target language and the originating language; 
 provide the enhanced description data in the originating language to the respective trained neural network; 
 translate, via the respective trained neural network, the enhanced description data from the originating language to the target language; and 
 
 generate a first graphical user interface (GUI) comprising:
 the enhanced description data for each transaction of the one or more transactions in the target language during the predetermined period; and 
 a selectable option associated with each transaction of the one or more transactions; 
 
 receive an indication, via the first GUI, that the user selected the selectable option associated with a first transaction of the one or more transactions; and 
 responsive to receiving the indication, cause the first GUI to additionally display the enhanced description data associated with the first transaction in the originating language. 
 
 
     
     
       11. The system of  claim 10 , wherein each trained neural network comprises a recurrent neural network with an encoder and a decoder. 
     
     
       12. The system of  claim 10 , wherein the location of the user is a billing location. 
     
     
       13. The system of  claim 11 , wherein identifying the target language comprises retrieving the location associated with the user and matching the location with a first location of a predetermined list of locations associated with the target language. 
     
     
       14. The system of  claim 10 , wherein the first GUI further comprises a flag associated with each transaction of the one or more transactions with the enhanced description data translated to the target language during the predetermined period, the flag indicating the enhanced description data was translated and showing the originating language and the target language. 
     
     
       15. The system of  claim 10 , wherein:
 the additional data comprises an address, a phone number, an email, and a uniform resource locator, and 
 the instructions are further configured to cause the system to transmit the first GUI to a user device associated with the user for display. 
 
     
     
       16. The system of  claim 10 , wherein the instructions are further configured to cause the system to identify the originating language based on the raw transaction description data using natural language processing. 
     
     
       17. A system, comprising:
 one or more processors; and 
 a memory in communication with the one or more processors and storing instructions are configured to cause the system to:
 receive or retrieve transaction description data in one or more originating languages, the transaction description data associated with one or more transactions made by a user during a predetermined period of time; 
 identify the originating language of the one or more originating languages associated with each transaction of the one or more transactions using a first neural network; 
 identify one or more names from the transaction description data; 
 retrieve additional data in the originating language based on the one or more names; 
 generate enhanced description data in the originating language for the user based on the transaction description data and the additional data for each of the one or more transactions during the predetermined period; 
 determine whether the enhanced description data for each transaction of the one or more transactions requires translation from the originating language to the target language; 
 responsive to determining the enhanced description data requires translation from the originating language to the target language:
 provide the enhanced description data in the originating language for each of the one or more transactions to a selected trained neural network of a plurality of trained neural networks; and 
 translate, via the selected trained neural network, the enhanced description data from the originating language to a target language; 
 
 generate a first graphical user interface (GUI) comprising the enhanced description data for each transaction of the one or more transactions during the predetermined period, wherein:
 for each transaction of the one or more transactions associated with enhanced description data requiring translation from the originating language to the target language, the first GUI displays;
 the enhanced description data in the target language with a flag indicating the enhanced description data was translated; 
 a selectable option, and 
 
 for each transaction of the one or more transactions associated with enhanced description data not requiring translation from the originating language to the target language, the first GUI displays the enhanced description data in the originating language; 
 
 receive an indication, via the first GUI, that the user selected the selectable option associated with a first transaction of the one or more transactions; 
 responsive to receiving the indication:
 cause the first GUI to additionally display the enhanced description data associated with the first transaction in the originating language; and 
 receive, via the first GUI, feedback instructions related to an accuracy of the enhanced description data in the target language. 
 
 
 
     
     
       18. The system of  claim 17 , wherein the instructions are further configured to cause the system to transmit the first GUI to a user device associated with the user for display. 
     
     
       19. The system of  claim 17 , wherein the instructions are further configured to cause the system to train the selected trained neural network based on the feedback instructions.

Cited by (0)

No later patents cite this yet.

References (0)

No backward citations on record.